 Piotr Wilkin
|
6798b69bcc
Some updates for Mr. Chunky
|
3 months ago |
|
Piotr Wilkin
|
912339a5c2
Proper (?) offsetting
|
3 months ago |
|
Piotr Wilkin
|
16b3f9c300
Valgrind debugging session / multi-chunk support
|
3 months ago |
|
Piotr Wilkin
|
5417f3294b
Wrong dimension order
|
3 months ago |
|
Piotr Wilkin
|
875de2bcc2
e steps forward, pi steps back
|
3 months ago |
|
Piotr Wilkin
|
a60458ebee
Remove more debug
|
3 months ago |
|
Piotr Wilkin
|
78e0fbd8f4
Remove debug
|
3 months ago |
|
Piotr Wilkin
|
9de7244c26
Fix memory corruption
|
3 months ago |
|
Piotr Wilkin
|
75586ea36e
Delta.net chunked reimplemented
|
3 months ago |
|
Piotr Wilkin
|
2cab86a09f
Let the debug out.
|
3 months ago |
|
Piotr Wilkin
|
7eef0bd948
Rewrite recurrent delta + softmax to separate ops
|
3 months ago |
|
Piotr Wilkin
|
0a9244acd0
The optimization worked even too well ;)
|
3 months ago |
|
Piotr Wilkin
|
477c1616ad
Parallelize delta_net
|
3 months ago |
|
Piotr Wilkin
|
666fc0583d
Parity on delta!
|
3 months ago |
|
Piotr Wilkin
|
c1e46f62fa
Achieve pre-chunk-attention parity; remove most of the LLM generated crap
|
3 months ago |
|
Piotr Wilkin
|
c87e8d550c
Tensor preparation for delta_net complete
|
3 months ago |
|
Piotr Wilkin
|
7ec2df64a4
Added: tri, cumsum. Still a mess.
|
3 months ago |
 Daniel Bevenius
|
3913f8730e
ggml : fix padding in timestep embedding kernels (#15932)
|
4 months ago |
|
Daniel Bevenius
|
9de447d94e
ggml-cpu : fix padding in ggml_timestep_embedding (#15917)
|
4 months ago |
 Xuan-Son Nguyen
|
9fcb29f22f
ggml: allow casting between f32 and i32 (#15783)
|
4 months ago |
 leejet
|
0a1b3982cd
ggml: add ops for WAN video model (cuda && cpu) (#15669)
|
4 months ago |
 compilade
|
73804145ab
ggml : fix SSM_SCAN for n_groups > 1 (#15625)
|
4 months ago |
 xctan
|
1cf123a343
ggml-cpu : add basic RVV support for vector f32 ops (#15057)
|
4 months ago |
 rmatif
|
92f7f0a53c
ggml: add `conv3d` op (#15182)
|
5 months ago |
 Jonathan Graehl
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
5 months ago |
 Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
|
Georgi Gerganov
|
64978340b0
ggml : add asserts (#14720)
|
6 months ago |
|
Xuan-Son Nguyen
|
98bab638fb
ggml : add ggml_scale_bias (#14417)
|
6 months ago |
 Sigbjørn Skjæret
|
28657a8229
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445)
|
6 months ago |
|
Georgi Gerganov
|
9067487c44
ggml : fix FA mask dim 2 and 3 (#14505)
|
6 months ago |
